Intelligent Footwear Material Recommendation System: Using Machine Learning For Refined Slip Resistance
Fuente:
Zenodo
Guardado en:
| Autores principales: | , |
|---|---|
| Formato: | Recurso digital |
| Lenguaje: | inglés |
| Publicado: |
Zenodo
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866901531978104832 |
|---|---|
| author | Thomas, Treesa Devis, Jinson |
| author_facet | Thomas, Treesa Devis, Jinson |
| contents | <p><span><span lang="EN-AU">Abstract</span></span><span lang="EN-AU"> - </span><span><span lang="EN-AU">Slip and fall incidents create major safety hazards in different settings because of the inappropriate choice of footwear. Conventional slip resistance standards do not consider user-specific factors and dynamic conditions. This article introduces an Intelligent Slip Resistance Recommender System, a machine learning system utilizing a Random Forest Classifier to suggest best footwear materials according to user input (age, weight, shoe size, activity type) and environmental conditions (surface type and conditions).The system consumes inputs through a multi-stage pipeline, encoding categorical variables and predicting material suitability with 92% accuracy, outperforming traditional methods. It offers context-aware recommendations, such as Vibram for outdoor rough surfaces and non-marking rubber for indoor polished floors. The web interface is easy to use, making it available to a wide audience of professionals and differently-abled users.This system connects material science, human factors, and AI to enhance workplace safety, mitigate fall hazards among the elderly, and optimize decision-making in footwear choice. Future development involves the extension of datasets and the inclusion of real-time environmental data for dynamic suggestions.</span></span></p> |
| format | Recurso digital |
| id | zenodo_https___doi_org_10_5281_zenodo_15486666 |
| institution | Zenodo |
| language | eng |
| publishDate | 2025 |
| publisher | Zenodo |
| record_format | zenodo |
| spellingShingle | Intelligent Footwear Material Recommendation System: Using Machine Learning For Refined Slip Resistance Thomas, Treesa Devis, Jinson Slip resistance, footwear recommendation, machine learning, Random Forest, surface conditions, personalized safety, predictive analytics, human-computer interaction. <p><span><span lang="EN-AU">Abstract</span></span><span lang="EN-AU"> - </span><span><span lang="EN-AU">Slip and fall incidents create major safety hazards in different settings because of the inappropriate choice of footwear. Conventional slip resistance standards do not consider user-specific factors and dynamic conditions. This article introduces an Intelligent Slip Resistance Recommender System, a machine learning system utilizing a Random Forest Classifier to suggest best footwear materials according to user input (age, weight, shoe size, activity type) and environmental conditions (surface type and conditions).The system consumes inputs through a multi-stage pipeline, encoding categorical variables and predicting material suitability with 92% accuracy, outperforming traditional methods. It offers context-aware recommendations, such as Vibram for outdoor rough surfaces and non-marking rubber for indoor polished floors. The web interface is easy to use, making it available to a wide audience of professionals and differently-abled users.This system connects material science, human factors, and AI to enhance workplace safety, mitigate fall hazards among the elderly, and optimize decision-making in footwear choice. Future development involves the extension of datasets and the inclusion of real-time environmental data for dynamic suggestions.</span></span></p> |
| title | Intelligent Footwear Material Recommendation System: Using Machine Learning For Refined Slip Resistance |
| topic | Slip resistance, footwear recommendation, machine learning, Random Forest, surface conditions, personalized safety, predictive analytics, human-computer interaction. |
| url | https://doi.org/10.5281/zenodo.15486666 |